© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 87089
    Prev
    Next
    INDEX
    Explanations

    high fat and lipids

    np_acts-logits-general · gemini-2.5-flash-lite

    content related to fats, lipids, and cholesterol in dietary or nutritional contexts.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi

    The neuron is specialized in spotting numeric data—quantities, percentages, and other number tokens—in scientific or technical text.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     philanthropic
    -0.81
     ASCII
    -0.79
     philanthropy
    -0.79
    𝙺
    -0.72
     malware
    -0.71
    vlá
    -0.71
     freue
    -0.70
     Congress
    -0.70
     jdbc
    -0.68
     kindness
    -0.67
    POSITIVE LOGITS
     fat
    3.48
     fats
    3.20
     lipids
    3.00
    fat
    2.81
     lipid
    2.78
    Fat
    2.64
     Fat
    2.58
     fatty
    2.50
     Fats
    2.38
     Fatty
    2.28
    Activations Density 0.120%

    No Known Activations